[ https://issues.apache.org/jira/browse/HBASE-9719?page=com.atlassian.jira.plugin.system.issuetabpanels:comment-tabpanel&focusedCommentId=14125204#comment-14125204 ]
Robert Yokota commented on HBASE-9719: -------------------------------------- For completeness, I added a fourth test (hbase-counter-app) to test that increments to counters are atomic. This is the same test as the one for Cassandra that demonstrated that counter operations are not atomic in Cassandra. As shown below, HBase counters behave correctly. https://github.com/rayokota/jepsen/commit/d670a8a5e088fde29adbe1f5e19405755797a51f 0 unrecoverable timeouts Collecting results. Writes completed in 200.045 seconds 2000 total 2000 acknowledged 2000 survivors All 2000 writes succeeded. :-D > Premptive Call Me Maybe HBase > ----------------------------- > > Key: HBASE-9719 > URL: https://issues.apache.org/jira/browse/HBASE-9719 > Project: HBase > Issue Type: Bug > Reporter: stack > Assignee: Robert Yokota > Fix For: 2.0.0 > > > Aphyr wrote an interesting article on C* [1]. Some awkward-looking issues > were turned up though it seems the author is purportedly doing nothing but > exercising the software within spec; he is just paying close attention to > what is being returned. > It does not look like Aphyr will be coming our way any time soon [2] -- > thanks Ian Varley -- but he could change his mind. Wouldn't it be coolio if > we'd already run his test suite and found any bugs and fixed them before he > came by? This issue is about running his article against hbase so we find > the embarrassing before he does. > 1. http://aphyr.com/posts/294-call-me-maybe-cassandra > 2. https://twitter.com/aphyr/status/335082835868254209 -- This message was sent by Atlassian JIRA (v6.3.4#6332)